Skip to content
Skills Library
Documents & office · Conversion & formats

excel-processor

/excel-processor

Read, transform, analyze, and generate Excel and CSV files. Use when a user asks to open a spreadsheet, process Excel data, merge CSVs, create pivot tables, clean up data, convert between Excel and CSV, add formulas, filter rows, or generate reports from tabular data. Handles .xlsx, .xls, and .csv.

Repository
skills ↗
Licence
Apache-2.0
Last repository change
25.10.2026

Assessment and security

98/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene13 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Read, transform, analyze, and generate Excel and CSV files. Use when a user asks to open a spreadsheet, process Excel data, merge CSVs, create pivot tables, clean up data, convert between Excel and CSV, add formulas, filter rows, or generate reports from tabular data. Handles .xlsx, .xls, and .csv.

Original author description

Read, transform, analyze, and generate Excel and CSV files. Use when a user asks to open a spreadsheet, process Excel data, merge CSVs, create pivot tables, clean up data, convert between Excel and CSV, add formulas, filter rows, or generate reports from tabular data. Handles .xlsx, .xls, and .csv.

How it works

  1. Overview
  2. Instructions
  3. Examples
  4. Guidelines
Original SKILL.md headings · 162 lines, 734 words
SKILL.md preview
---
name: excel-processor
description: >-
  Read, transform, analyze, and generate Excel and CSV files. Use when a user
  asks to open a spreadsheet, process Excel data, merge CSVs, create pivot
  tables, clean up data, convert between Excel and CSV, add formulas, filter
  rows, or generate reports from tabular data. Handles .xlsx, .xls, and .csv.
license: Apache-2.0
compatibility: "Requires Python 3 with pandas 3.x and openpyxl; xlrd only for legacy .xls files"
metadata:
  author: terminal-skills
  version: "1.1.0"
  category: data-ai
  tags: "excel, csv, spreadsheet, data, pandas"
  repository: https://github.com/pandas-dev/pandas
---

# Excel Processor

## Overview

Read, transform, analyze, and generate Excel and CSV files using Python. This skill covers data loading, cleaning, filtering, aggregation, formula generation, and export to multiple formats.

## Instructions

When a user asks you to work with spreadsheets, Excel files, or CSV data, follow these steps:

### Step 1: Load the data

```python
import pandas as pd

# For .xlsx files (openpyxl engine, the default)
df = pd.read_excel("data.xlsx", sheet_name=0)  # or sheet_name="Sheet1"

# For legacy .xls files, install xlrd (pip install xlrd) or pass engine="calamine"
# df = pd.read_excel("legacy.xls", sheet_name=0, engine="calamine")

# For CSV files
df = pd.read_csv("data.csv")

# Show shape and preview
print(f"Shape: {df.shape[0]} rows x {df.shape[1]} columns")
print(f"Columns: {list(df.columns)}")
print(df.head())
```

Always print the shape, column names, and first few rows so the user can verify the data loaded correctly.

### Step 2: Assess data quality

```python
# Check for issues
print(f"Missing values:\n{df.isnull().sum()}")
print(f"\nDuplicates: {df.duplicated().sum()}")
print(f"\nData types:\n{df.dtypes}")
```

Report any issues found before proceeding with transformations.

### Step 3: Apply requested transformations

Common operations:

**Filtering:**
```python
filtered = df[df["status"] == "active"]
filtered = df[df["amount"] > 1000]
filtered = df[df["date"].between("2024-01-01", "2024-12-31")]
```

**Aggregation:**
```python
summary = df.groupby("category").agg(
    count=("id", "count"),
    total=("amount", "sum"),
    average=("amount", "mean")
).reset_index()
```

**Pivot tables:**
```python
pivot = df.pivot_table(
    values="revenue",
    index="region",
    columns="quarter",
    aggfunc="sum",
    margins=True
)
```

**Cleaning:**
```python
df["name"] = df["name"].str.strip().str.title()
df["email"] = df["email"].str.lower()
# State the format: without it pandas guesses per value and warns
df["date"] = pd.to_datetime(df["date"], format="%Y-%m-%d", errors="coerce")
df = df.drop_duplicates(subset=["id"])
df = df.dropna(subset=["required_field"])
```

### Step 4: Export results

```python
# To .xlsx (openpyxl writes the values; pandas does not apply cell styling)
with pd.ExcelWriter("output.xlsx", engine="openpyxl") as writer:
    df.to_excel(writer, sheet_name="Data", index=False)
    summary.to_excel(writer, sheet_name="Summary", index=False)

# To CSV
df.to_csv("output.csv", index=False)
```

### Step 5: Report what was done

Always summarize the operations performed, rows affected, and output file location.

## Examples

### Example 1: Clean and deduplicate a customer list

**User request:** "Clean up customers.xlsx -- remove duplicates, fix phone formatting, and split into active/inactive sheets"

**Actions taken:**
1. Load `customers.xlsx` (2,340 rows, 8 columns)
2. Remove 156 duplicate rows based on email
3. Standardize phone numbers to (XXX) XXX-XXXX format
4. Split into active (1,847 rows) and inactive (337 rows)
5. Export to `customers_clean.xlsx` with two sheets

**Output:**
```
Loaded: 2,340 rows x 8 columns
Removed: 156 duplicate rows (by email)
Fixed: 892 phone numbers reformatted
Split: 1,847 active, 337 inactive

Saved to customers_clean.xlsx:
  - Sheet "Active": 1,847 rows
  - Sheet "Inactive": 337 rows
```

### Example 2: Generate a monthly sales summary

**User request:** "Create a pivot table from sales.csv showing revenue by region and month"

**Actions taken:**
1. Load `sales.csv` (15,200 rows)
2. Parse date column, extract month
3. Build pivot table: regions as rows, months as columns, sum of revenue
4. Add row and column totals
5. Export to `sales_summary.xlsx`

**Output:**
```
| Region    | Jan      | Feb      | Mar      | Total     |
|-----------|----------|----------|----------|-----------|
| North     | $45,200  | $52,100  | $48,900  | $146,200  |
| South     | $38,700  | $41,300  | $44,600  | $124,600  |
| East      | $51,900  | $49,800  | $55,200  | $156,900  |
| West      | $42,100  | $46,700  | $43,500  | $132,300  |
| Total     | $177,900 | $189,900 | $192,200 | $560,000  |

Saved to sales_summary.xlsx
```

## Guidelines

- Always show data shape and column names after loading so the user can verify correctness.
- When dealing with dates, explicitly parse them with `pd.to_datetime()` and specify the format when ambiguous (e.g., is 01/02/03 Jan 2 or Feb 1?). Without `format=`, pandas 3 parses each value separately and emits a "Could not infer format" warning, which is slower and can silently mix day-first and month-first dates.
- `.xls` (Excel 97-2003) needs `xlrd` or `engine="calamine"`; `.xlsx` needs `openpyxl`. A `sheet_name` that does not exist raises `ValueError: Worksheet named ... not found`.
- Excel rows are capped at 1,048,576 per sheet; split larger exports across sheets or CSV files.
- For large files (100k+ rows), warn about memory and suggest chunked processing.
- Preserve original files. Write output to new files unless the user explicitly asks to overwrite.
- When merging multiple files, check that column names match and report any discrepancies before proceeding.
- If the user asks for "formulas", generate the Excel formula strings (e.g., `=SUM(B2:B100)`) rather than computing values, so the spreadsheet stays dynamic.
- Default to UTF-8 encoding for CSV. If the data contains special characters, test with `encoding="utf-8-sig"` for Excel compatibility.
Files in this package (2)
  • SKILL.md 6 KB
  • _scores.json 3 KB

Versions

The database has no other skills named excel-processor.

Database snapshot: 13.11.2026 · package version e455212ec2bc (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100excel-analysis
    Analyze Excel spreadsheets, create pivot tables, generate charts, and perform data analysis. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.
  • 100xlsx
    Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new…
  • 95Xlsx
    Create, read, analyze Excel workbooks — formulas, financial models, data analysis, recalculation, and CSV/TSV conversion. USE WHEN xlsx, Excel, spreadsheet, formulas, financial model, data analysis.
  • 100xlsx
    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file; create a new spreadsheet from scratch or from other data sources; analyze data and…
  • 95Xlsx
    Create, read, analyze Excel workbooks — formulas, financial models, data analysis, recalculation, and CSV/TSV conversion. USE WHEN xlsx, Excel, spreadsheet, formulas, financial model, data analysis.
  • 100spreadsheet-analyst
    Read, analyze, and produce Excel/CSV files - cleanup, pivots, formulas, charts, and formatted workbooks - using pandas and openpyxl. Use for any spreadsheet task.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.